Hugging Face
Models
Datasets
Spaces
Posts
Docs
Solutions
Pricing
Log In
Sign Up
zfz1
/
deepseek-8b-orpo-full
like
0
Text Generation
Transformers
TensorBoard
Safetensors
zfz1/my_preference_gsm8k_deepseek
llama
alignment-handbook
trl
orpo
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
License:
other
Model card
Files
Files and versions
Metrics
Training metrics
Community
Train
Deploy
Use this model
main
deepseek-8b-orpo-full
/
generation_config.json
zfz1
Model save
9adce4c
verified
4 months ago
raw
Copy download link
history
blame
contribute
delete
Safe
121 Bytes
{
"_from_model_config"
:
true
,
"bos_token_id"
:
100000
,
"eos_token_id"
:
100001
,
"transformers_version"
:
"4.42.3"
}